© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15652
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and syntax

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spikes on numeric literals (tokens containing digits) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berikan
    -1.27
     skak
    -1.25
     zimowa
    -1.21
     actrice
    -1.18
    Leírás
    -1.17
     PÅ
    -1.16
     tiada
    -1.16
     zima
    -1.15
     måneder
    -1.15
     gunakan
    -1.15
    POSITIVE LOGITS
    <bos>
    1.01
    そのため
    0.98
    th
    0.97
     both
    0.95
    G
    0.93
     ähnlich
    0.93
    `
    0.91
    èo
    0.91
     septum
    0.90
     beitragen
    0.90
    Activations Density 0.022%

    No Known Activations